ClawHub

Elevenlabs

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only ElevenLabs helper whose API-key use and external audio generation fit its stated healthcare TTS purpose, with privacy cautions needed for clinical data.

Install only if sending requested text to ElevenLabs is acceptable in your environment. Do not send PHI, patient identifiers, or regulated clinical content unless your organization has approved ElevenLabs for that use, appropriate compliance controls are in place, and the API key is stored securely.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The README presents the skill as a clinical text-to-speech capability, but also expands scope to music generation. This mismatch increases the chance that agents or users enable broader functionality than expected, which is risky in a healthcare context because it changes data flow and model behavior beyond the declared purpose.

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The README adds a music-generation feature that is not justified by the stated purpose of converting text to speech. Hidden or under-declared capabilities are dangerous because they undermine least privilege and informed deployment, especially where clinical users may assume only TTS processing is occurring.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs users to send clinical text to ElevenLabs but does not clearly warn that this content is transmitted to an external third-party service. In a healthcare context, users may include PHI or sensitive medical content, creating privacy, compliance, and consent risks even though the skill briefly advises against logging or sending sensitive data without making the external transfer risk explicit to the user.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal